To calculate flow parameters of a vaneless diffuser of the centrifugal compressor stage, it is sufficient to determine the loss coefficient and the flow direction at the outlet. The paper presents the results of modeling the characteristics of these two parameters using neural networks and CFD methods. To obtain mathematical models, ANSYS calculation data was used for vaneless diffusers with a relative width of 0.014–0.1, relative outlet diameter of 1.4–2.0, inlet flow angle of 10–90° and velocity coefficient of 0.39–0.82, with the Reynolds number being in the range of 87 500–1 030 000. A comparison with the theory showed the regularity of gas-dynamic characteristics, and comparison with well-known experiments showed the correspondence of the flow structure. In order to improve the accuracy of simulation using neural networks, various recommendations on the preparation and processing of the initial data were collected and tested: identification of conflict examples and outliers, data normalization, improving the quality of the neural network training under the insufficient amount of sampling, etc. The application of the aforementioned recommendations significantly improved the accuracy of simulation. A simulation experiment based on neural models for studying the influence of dimensions, diffuser shape and similarity criteria on the diffuser gas dynamic characteristics made it possible to verify physical adequacy of the mathematical models, obtain new data on energy conversion processes and produce a set of recommendations on the optimal design of vaneless diffusers.